NXP backend: improve mapping algorithm (pytorch#22614)

### Summary
Improve NXP Neutron operator-to-Edge profiling map

1. Improve TFLite-to-Neutron mapping algorithm
- Filter tensor I/O to dynamic (Variable) tensors only, excluding
constants
- Group Neutron subgraphs into linearly-connected execution chains based
on matching dynamic I/O tensor names
- Match each Neutron chain to a corresponding TFLite operator chain by
comparing boundary inputs and outputs

2. Fix mapping for batch > 1
- Enable `dumpMicrocode` in the converter log to include the
Microinstructions section
- Remap NeutronOperator locations and kernel counts using the actual
CALLARGS sequence from the microcode, which accounts for batch
repetitions and converter-injected helper kernels (e.g. MemCpy)

3. Fix profiling time scaling
- Neutron profiling timestamps are measured in clock cycles; divide by
the Neutron NPU frequency to convert to seconds


### Test plan
Tests included


cc @robert-kalmar @JakeStevens @digantdesai @rascani

Author: irtrukhina

backends/nxp/backend/neutron_compiler_manager.py

@@ -41,14 +41,18 @@ def _build_compilation_context(compilation_opts):
     cctx.compilationOpts.dumpKernelSelectionCode = compilation_opts[
         "dumpKernelSelectionCode"
     ]
-    if (
-        hasattr(cctx.compilationOpts, "useProfiling")
-        and compilation_opts["useProfiling"]
-    ):
-        cctx.compilationOpts.useProfiling = compilation_opts["useProfiling"]
+    if compilation_opts["useProfiling"]:
+        if not _USING_NEUTRON_COMPILER:
+            raise RuntimeError(
+                "Profiling requires eIQ Neutron SDK >= 3.2.1. "
+                "The installed SDK (neutron_converter-based, <= 3.2.0) does not provide neutronGetSdkVersion(); "
+                "the ExecuTorch runtime will fail to link. Upgrade the SDK."
+            )
+        cctx.compilationOpts.useProfiling = True
         cctx.compilationOpts.dumpAfterImport = "console"
         cctx.compilationOpts.dumpAfterGenerate = "console"
-        cctx.compilationOpts.verbose = compilation_opts["useProfiling"]
+        cctx.compilationOpts.verbose = True
+        cctx.compilationOpts.dumpMicrocode = True
 
     return cctx